Communications of the ACM
Computational limitations on learning from examples
Journal of the ACM (JACM)
Searching with known error probability
Theoretical Computer Science
Lower Bound Methods and Separation Results for On-Line Learning Models
Machine Learning - Computational learning theory
Machine Learning
Machine Learning
Learning unions of two rectangles in the plane with equivalence queries
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
On-line learning of rectangles in noisy environments
COLT '93 Proceedings of the sixth annual conference on Computational learning theory
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Learning unions of boxes with membership and equivalence queries
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Geometrical concept learning and convex polytopes
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
Learning from a consistently ignorant teacher
COLT '94 Proceedings of the seventh annual conference on Computational learning theory
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
Noise-tolerant parallel learning of geometric concepts
COLT '95 Proceedings of the eighth annual conference on Computational learning theory
A composition theorem for learning algorithms with applications to geometric concept classes
STOC '97 Proceedings of the twenty-ninth annual ACM symposium on Theory of computing
Online Learning versus Offline Learning
Machine Learning
A new composition theorem for learning algorithms
STOC '98 Proceedings of the thirtieth annual ACM symposium on Theory of computing
Learning functions represented as multiplicity automata
Journal of the ACM (JACM)
Intrinsic Complexity of Learning Geometrical Concepts from Positive Data
COLT '01/EuroCOLT '01 Proceedings of the 14th Annual Conference on Computational Learning Theory and and 5th European Conference on Computational Learning Theory
| Hi-index | 0.00 |
This paper solves the following open problem: Is there an algorithmfor on-line learning of rectangles i=1dai,ai+1,…,bi}over a discrete domain{1,…,n}dwhose error bound is polylogarithmic in the sizend of the domain(i.e. polynomial in d and logn )? We give a positive solution byintroducing a new design technique that appears to be of some intereston its own. The new learning algorithm for rectangles consists of2d separate search strategies thatsearch for the parameters a1,b1,…,ad,bdof the target rectangle. A learning algorithm with this type of modulardesign ends to fail because of the well known “credit assignmentproblem”: Which of the 2d localsearch strategies should be “blamed” when the globalalgorithm makes an error? We overcome this difficulty by employing localsearch strategies (“error tolerant binary search”) that areable to tolerate certain types of wrong credit assignments.Section 4 contains another application of this design technique: analgorithm for learning the union of two rectangles in the plane.